def compress(input_file, output_path):
''' Compress input_file, store it in output_path and then
return output_file '''
# Get file name and extension
input_filename, input_fileext = os.path.splitext(
os.path.basename(input_file))
output_filename = input_filename + '.huffman'
output_file = os.path.join(output_path, output_filename)
print(output_file + " aa")
with open(input_file, 'r') as f:
data = f.read()
f.close()
# Get frequency table from data
frequencies = collections.Counter(data)
root = build_tree(frequencies)
encoded_str = utility.get_encoded_str(root, data)
padded_encoded_str = utility.pad_encoded_str(encoded_str)
byte_data = utility.get_byte_array(padded_encoded_str)
with open(output_file, 'wb') as out:
# Serialize data to file
pickle.dump((frequencies, byte_data), out)
out.close()
return output_file
def test_get_encoded_str(self):
data = 'ABB'
n1 = Node('A', 1)
n2 = Node('B', 2)
root = Node('', 3, n2, n1)
encoded_str = utility.get_encoded_str(root, data)
assert encoded_str == '100'
def test_get_decoded_str(self):
data = 'aab'
n1 = Node('a', 2)
n2 = Node('b', 1)
root = Node('', 3, n2, n1)
encoded_str = utility.get_encoded_str(root, data)
decoded_str = utility.get_decoded_str(root, encoded_str)
assert decoded_str == data
def compress(input_file, output_path):
input_filename, input_fileext = os.path.splitext(
os.path.basename(input_file))
output_filename = input_filename + '.fano'
output_file = os.path.join(output_path, output_filename)
with open(input_file, 'r') as f:
data = f.read()
frequencies = collections.Counter(data)
nodes = create_nodes_from_frequencies(frequencies)
root = build_tree(nodes)
codes = utility.get_codes(root)
encoded_str = utility.get_encoded_str(root, data)
padded_encoded_str = utility.pad_encoded_str(encoded_str)
byte_array = utility.get_byte_array(padded_encoded_str)
with open(output_file, 'wb') as out:
# Serialize data to file
pickle.dump((frequencies, byte_array), out)
return output_file